Katalog Plus
Bibliothek der Frankfurt UAS
Bald neuer Katalog: sichern Sie sich schon vorab Ihre persönlichen Merklisten im Nutzerkonto: Anleitung.
Dieses Ergebnis aus BASE kann Gästen nicht angezeigt werden.  Login für vollen Zugriff.

Enhancing SQL Injection Detection with Long Short-Term Memory Networks in Deep Learning

Title: Enhancing SQL Injection Detection with Long Short-Term Memory Networks in Deep Learning
Authors: Takyi, Kate; Gyening, Rose-Mary Owusuaa Mensah; Kobinnah, Miriam; Boateng, Maxwell Akwasi; Boadu-Acheampong, Samuelson
Contributors: Kwame Nkrumah University of Science and Technology, Computer Science Department
Source: International Journal of Open Information Technologies; Vol 13, No 1 (2025); 7-13 ; 2307-8162
Publisher Information: International Journal of Open Information Technologies
Publication Year: 2025
Collection: International Journal of Open Information Technologies (INJOIT)
Description: The security risks posed by (Structured Queried Language) SQL injection attacks in web applications necessitate more advanced detection methods beyond conventional techniques. Deep learning methods such as Long Short-Term Memory (LSTM) networks have been employed to detect SQL injection because they can handle sequential data such as SQL queries. In SQL datasets, imbalances arise due to the infrequent presence of malicious SQL queries. In this study, we employ data augmentation techniques that mitigate this issue and enable robust model training. The augmentation involves substituting keywords with randomly selected synonyms exclusively within malicious SQL queries. This augmentation approach is implemented on a sizable dataset, resulting in 89,143 samples post-augmentation, distinguishing this research from the prevailing literature that predominantly employs smaller datasets. The outcomes underscore the model's robustness, yielding 99.4% accuracy, precision, and F1 score. Compared to LSTM-based methodologies for SQL injection (SQLi) detection, the proposed approach showcases superior accuracy and efficiency in identifying potential threats. This research significantly fortifies cybersecurity measures for online applications and databases.
Document Type: article in journal/newspaper
File Description: application/pdf
Language: English
Relation: http://injoit.org/index.php/j1/article/view/1978/1823; http://injoit.org/index.php/j1/article/downloadSuppFile/1978/877; http://injoit.org/index.php/j1/article/view/1978
Availability: http://injoit.org/index.php/j1/article/view/1978
Rights: Copyright (c) 2025 International Journal of Open Information Technologies
Accession Number: edsbas.649A3D41
Database: BASE